b-karl

We use Claude Code in our company and I also agree memories go stale and pollute the context over time, especially when the state changes externally. E.g. someone does a refactor or introduces a pattern and I was not involved in developing it so my local memories did not get aligned.

My most recent example were some deprecated and archived repos that kept getting added to plans for patching issues.

We use a private Claude plugin marketplace for internal plugins and skills and I try to regularly prune my memory, migrating relevant stuff to a proper home (skills in the marketplace, docs in repos or Notion etc) and prune outdated information.

Cursor supports all the Claude file patterns, including plugins and marketplaces. We leverage that to support both Claude and Cursor with same instructions and skills

Not a catch all to fix issues agree with linting. Being very strict with linters has become very cheap with coding agents and it keeps you up to date with code standards and keeps code style homogenous which is very nice when you are reviewing professional code, regardless of who wrote it.

It’s also tricky otherwise if you have to occasionally review lazily written manual code mixed with syntactically formal/clean but functionally incorrect AI code.

In Excel you have goal seek for this functionality. I believe it does some form of numerical solving of the equation system.

Good for every situation when you need to solve equations!

In the context of using spreadsheets I think about solving simple financial or maybe construction/mechanical design problems where you don’t want to solve it manually or program it and a spreadsheet is a quick and useful interface.

There are both, the router is further down the page

I started using keyboard navigation more and more around Win 7 and that has actually improved quite consistently since then and I remember Win 8 Win-key search was quite good, if you could look past the start menu…

Also reminds me of the layers of UI versions still present in Windows https://news.ycombinator.com/item?id=27556754

The field of AI has become very big in the recent years and people are becoming more and more specialized just like the in the rest of software or R&D. There’s all sorts of model building and development, integration in other traditional software, infrastructure, deployment and devops and now also all the governance and compliance for a lot of fields. It’s good for people working in those stacks to understand the full chain at some level but pretty fast you will have experts in particular parts of the chain and no one will understand it all.

And then there’s of course career climbers playing politics and people getting into the field because of interest or resume building.

So maybe we are talking too much about AI as a tech bubble (like the dotcom bubble) and it is actually closer to an arms race like the nuclear programs or space race? For better and for worse there are a lot of secondary value and ventures created from those and one could see AI ventures in a similar light.

A key difference is of course, at least in the US, that the research is led by corporations as opposed to research institutes and government.

Completely agree. I think this was kind of solved going to university where most of the math courses did not allow calculators and similar tools or books present and the tests were designed to not require these and instead focused on theory and concepts. I think isolating test environments is one thing and then you can in addition have classes or assignments where AI and other tools are available and acceptable to use.

I was part of designing a user file upload, it was a B2B product,limited number of users and in principle trusted users but similar to other comments we did something like:

- some file type and size checks in web app

- pre-signed URL

- upload bucket

- lambdas for processing and sanity checks

- processed bucket

I have not done the 1 on 1 method before, it sounds interesting and will try it in the future, but I agree with utilizing the grace period to explore, ask and learn as much as possible about the organization and industry.

My additional recommendation would be to try to identify limited-scope projects that contribute to your role and where you can start delivering some value. For me this helps set a clear goal and it is usually easier to identify the specific skills/knowledge/information/contacts I need to complete the task. It also usually feels motivating to check off those early projects.

Live in Sweden and I think we currently have pretty good competition in the delivery service market. Home delivery, staffed pick up points and unmanned parcel cabinets are usually available options from many online vendors, and the latter two often support electronic identification.

I think having multiple options is a good way of decoupling the UX of the delivery service with the UX of the retailer since the user is choosing the delivery service. If your only option is FedEx or UPS and you have a bad experience, that will hurt your trust in the retailer as well. But if you have several options for delivery and one fails you might instead stop using that delivery service/option when possible and opt for a different one next time.